On the person and psychophysiological state identification using electroencephalogram parameters

Abstract

The development of methods and technologies for the automatic determination of the psychophysiological state (PPS) of a person is an actual scientific and technical task. Early detection of the fact that the subject is in a sleepy state or in a state of intoxication at the workplace will help to avoid accidents, harm to life, health, and causing losses. In this work the EEG data of 30 subjects in normal, sleepy conditions and a state of mild intoxication were collected. As a result of the spectral and correlation analysis of the EEG data features were selected. An amount of information about the difference of the investigated states contained in the features was determined. A computational experiment on the recognition of human state according to EEG data based on the “naive” Bayes classifier was conducted. The following error level was achieved: 10.9% when recognizing the state of “norm” and “intoxication”; 0.2% when recognizing the status of “normal” and “falling asleep.”